Chat Completion Object

Structure of the Chat Completion object and the Chat Completion Chunk streaming object

Chat Completion Object

The Chat Completions API returns two object types: non-streaming responses return a ChatCompletion object, and streaming responses return ChatCompletionChunk objects.

Chat Completion Object

The complete response object returned by non-streaming requests.

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1709123456,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 15,
    "total_tokens": 27
  },
  "system_fingerprint": "fp_abc123"
}

Field Descriptions

Field	Type	Description
id	string	Unique identifier for this completion
object	string	Always chat.completion
created	integer	Unix timestamp of creation time
model	string	The model name actually used
choices	array	List of completion results, length determined by the n request parameter
choices[].index	integer	Index of the result in the list
choices[].message	object	The message generated by the model
choices[].message.role	string	Always assistant
choices[].message.content	string|null	Text content of the message
choices[].message.tool_calls	array|null	List of tools the model requests to call
choices[].finish_reason	string	Stop reason: stop, length, tool_calls, content_filter
usage	object	Token usage statistics
usage.prompt_tokens	integer	Number of input tokens
usage.completion_tokens	integer	Number of output tokens
usage.total_tokens	integer	Total number of tokens
system_fingerprint	string|null	System fingerprint

---

Chat Completion Chunk Object (Streaming)

During streaming requests, the server returns ChatCompletionChunk objects in SSE (Server-Sent Events) format, chunk by chunk.

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion.chunk",
  "created": 1709123456,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "delta": {
        "role": "assistant",
        "content": "Hello"
      },
      "finish_reason": null
    }
  ]
}

Field Descriptions

Field	Type	Description
id	string	Unique identifier for this completion, shared across all chunks
object	string	Always chat.completion.chunk
created	integer	Unix timestamp of creation time
model	string	The model name actually used
choices	array	List of incremental results
choices[].index	integer	Index of the result in the list
choices[].delta	object	Incremental message content
choices[].delta.role	string	Only appears in the first chunk, value is assistant
choices[].delta.content	string	Incremental text content
choices[].delta.tool_calls	array	Incremental tool calls
choices[].finish_reason	string|null	Stop reason in the last chunk, null for all others
usage	object|null	Only included in the last chunk when stream_options.include_usage is true

Streaming Format

Streaming responses follow the SSE protocol. Each event is prefixed with data: , and the stream ends with data: [DONE]:

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1709123456,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Crazyrouter is fully compatible with the OpenAI Chat Completion object format and supports all standard fields. Additional fields returned by upstream models are also passed through to the client.